dna3bs.hpp

Go to the documentation of this file.

// SPDX-FileCopyrightText: 2006-2025 Knut Reinert & Freie Universität Berlin
// SPDX-FileCopyrightText: 2016-2025 Knut Reinert & MPI für molekulare Genetik
// SPDX-License-Identifier: BSD-3-Clause

 
#pragma once
 
#include <vector>
 
#include <seqan3/alphabet/nucleotide/nucleotide_base.hpp>
#include <seqan3/utility/char_operations/transform.hpp>
 
// ------------------------------------------------------------------
// dna3bs
// ------------------------------------------------------------------
 
namespace seqan3
{
class dna3bs : public nucleotide_base<dna3bs, 3>
{
private:
    using base_t = nucleotide_base<dna3bs, 3>;

    friend base_t;
    friend base_t::base_t;
 
public:
    constexpr dna3bs() noexcept = default;                           
    constexpr dna3bs(dna3bs const &) noexcept = default;             
    constexpr dna3bs(dna3bs &&) noexcept = default;                  
    constexpr dna3bs & operator=(dna3bs const &) noexcept = default; 
    constexpr dna3bs & operator=(dna3bs &&) noexcept = default;      
    ~dna3bs() noexcept = default;                                    
 
    using base_t::base_t;
 
private:
    static constexpr char_type rank_to_char_table[alphabet_size]{'A', 'G', 'T'};

    static constexpr rank_type rank_complement_table[alphabet_size]{
        2, // T is complement of 'A'_dna3bs
        2, // T is complement of 'G'_dna3bs
        0  // A is complement of 'T'_dna3bs
    };

    static constexpr rank_type rank_complement(rank_type const rank)
    {
        return rank_complement_table[rank];
    }

    static constexpr char_type rank_to_char(rank_type const rank)
    {
        return rank_to_char_table[rank];
    }

    static constexpr rank_type char_to_rank(char_type const chr)
    {
        using index_t = std::make_unsigned_t<char_type>;
        return char_to_rank_table[static_cast<index_t>(chr)];
    }

    static constexpr std::array<rank_type, 256> char_to_rank_table{[]() constexpr
                                                                   {
                                                                       std::array<rank_type, 256> ret{};
 
                                                                       // reverse mapping for characters and their lowercase
                                                                       for (size_t rnk = 0u; rnk < alphabet_size; ++rnk)
                                                                       {
                                                                           ret[rank_to_char_table[rnk]] = rnk;
                                                                           ret[to_lower(rank_to_char_table[rnk])] = rnk;
                                                                       }
 
                                                                       // set C and U equal to T
                                                                       ret['C'] = ret['T'];
                                                                       ret['c'] = ret['t'];
                                                                       ret['U'] = ret['T'];
                                                                       ret['u'] = ret['t'];
 
                                                                       // iupac characters get special treatment, because there is no N
                                                                       ret['R'] = ret['A'];
                                                                       ret['r'] = ret['A']; // A or G becomes A
                                                                       ret['Y'] = ret['T'];
                                                                       ret['y'] = ret['T']; // C or T becomes T
                                                                       ret['S'] = ret['T'];
                                                                       ret['s'] = ret['T']; // C or G becomes T
                                                                       ret['W'] = ret['A'];
                                                                       ret['w'] = ret['A']; // A or T becomes A
                                                                       ret['K'] = ret['G'];
                                                                       ret['k'] = ret['G']; // G or T becomes G
                                                                       ret['M'] = ret['A'];
                                                                       ret['m'] = ret['A']; // A or C becomes A
                                                                       ret['B'] = ret['T'];
                                                                       ret['b'] = ret['T']; // C or G or T becomes T
                                                                       ret['D'] = ret['A'];
                                                                       ret['d'] = ret['A']; // A or G or T becomes A
                                                                       ret['H'] = ret['A'];
                                                                       ret['h'] = ret['A']; // A or C or T becomes A
                                                                       ret['V'] = ret['A'];
                                                                       ret['v'] = ret['A']; // A or C or G  becomes A
 
                                                                       return ret;
                                                                   }()};
};
 
// ------------------------------------------------------------------
// containers
// ------------------------------------------------------------------

using dna3bs_vector = std::vector<dna3bs>;
 
// ------------------------------------------------------------------
// literals
// ------------------------------------------------------------------
inline namespace literals
{

constexpr dna3bs operator""_dna3bs(char const c) noexcept
{
    return dna3bs{}.assign_char(c);
}

SEQAN3_WORKAROUND_LITERAL dna3bs_vector operator""_dna3bs(char const * s, std::size_t n)
{
    dna3bs_vector r;
    r.resize(n);
 
    for (size_t i = 0; i < n; ++i)
        r[i].assign_char(s[i]);
 
    return r;
}

 
} // namespace literals
 
} // namespace seqan3